Back to Strategies
Agent (0-10 Scores)
Multi-Step Agent (0-10 Scores)
Agent (0-10 Scores)Claude & GPT-4
5-step agent pipeline producing numeric 0-10 scores. Same multi-step architecture as the categorical agent but outputs calibrated numeric predictions instead of categories.
Overview
Strategy Type
Agent (0-10 Scores)
Number of Steps
5 steps
Models Used
Claude & GPT-4
Output Format
Numeric (0-10 scale)
Pipeline Visualization
1
Step 1: Extract Facts
LLM prompt execution
2
Step 2: Web Search
Automated web search (no LLM call)
3
Step 3: Clinical Assessment
LLM prompt execution
4
Step 4: Market Dynamics
LLM prompt execution
5
Step 5: Final Score
LLM prompt execution
Prompt Details
1
Step 1: Extract Facts
You are a biotech analyst extracting key facts from press releases.
Extract key facts from this press release:
{pr_text}
Return JSON:
{{
"primary_endpoint_met": true/false/null,
"p_value": "<value or null>",
"effect_size": "<key metric>",
"safety_signals": ["list"],
"regulatory_status": "<status or null>",
"trial_phase": "<phase>",
"key_quotes": ["1-2 quotes"]
}}
Expected Output Format
This prompt expects a JSON response. See the user prompt template for the exact structure.
2
Step 2: Web Search
Automated(Automated web search step)
Search for {ticker} stock biotech news and {drug} {company} analyst views
3
Step 3: Clinical Assessment
You are a clinical trial expert.
Assess clinical significance:
FACTS: {step1_result}
DRUG: {drug}, PHASE: {phase}, INDICATION: {indication}
Return JSON:
{{
"clinical_significance": "breakthrough/meaningful/incremental/neutral/disappointing/failure",
"vs_standard_of_care": "<comparison>",
"approvability": "likely/uncertain/unlikely",
"reasoning": "<2 sentences>"
}}
Expected Output Format
This prompt expects a JSON response. See the user prompt template for the exact structure.
4
Step 4: Market Dynamics
You are a biotech equity analyst.
Evaluate market dynamics:
CLINICAL: {step3_result}
MARKET: {step2_result}
TICKER: {ticker}, DRUG: {drug}, EVENT: {cat_type}
Return JSON:
{{
"priced_in": "fully/partially/not/negative",
"expectations": "exceeded/met/missed",
"asset_importance": "lead/key/minor",
"reasoning": "<2 sentences>"
}}
Expected Output Format
This prompt expects a JSON response. See the user prompt template for the exact structure.
5
Step 5: Final Score
You are a senior biotech analyst predicting stock moves.
Score 0-10:
- 0: Catastrophic (>20% drop)
- 1-2: Very negative (10-20% drop)
- 3-4: Negative (5-10% drop)
- 5: Neutral (<5% move)
- 6-7: Positive (5-10% rise)
- 8-9: Very positive (10-20% rise)
- 10: Exceptional (>20% rise)
Be calibrated. Most expected approvals = 5-6.
Make final prediction:
FACTS: {step1_result}
CLINICAL: {step3_result}
MARKET: {step4_result}
TICKER: {ticker}, DRUG: {drug}
Return JSON:
{{
"score": <0-10>,
"confidence": <0-100>,
"reasoning": "<2-3 sentences>",
"key_factors": ["factor1", "factor2"]
}}
Expected Output Format
This prompt expects a JSON response. See the user prompt template for the exact structure.
Template Variables Reference
These variables are dynamically replaced with actual values when the strategy is executed:
{cat_type}Catalyst event type (e.g., FDA approval, trial results){company}Company name{drug}Drug or therapy name{indication}Medical indication/disease being treated{phase}Clinical trial phase (1, 2, 3, etc.){pr_text}Full press release text{step1_result}Output from Step 1 prompt{step2_result}Output from Step 2 (web search){step3_result}Output from Step 3 prompt{step4_result}Output from Step 4 prompt{ticker}Company stock ticker symbol{{
"clinical_significance": "breakthrough/meaningful/incremental/neutral/disappointing/failure",
"vs_standard_of_care": "<comparison>",
"approvability": "likely/uncertain/unlikely",
"reasoning": "<2 sentences>"
}Custom variable{{
"priced_in": "fully/partially/not/negative",
"expectations": "exceeded/met/missed",
"asset_importance": "lead/key/minor",
"reasoning": "<2 sentences>"
}Custom variable{{
"primary_endpoint_met": true/false/null,
"p_value": "<value or null>",
"effect_size": "<key metric>",
"safety_signals": ["list"],
"regulatory_status": "<status or null>",
"trial_phase": "<phase>",
"key_quotes": ["1-2 quotes"]
}Custom variable{{
"score": <0-10>,
"confidence": <0-100>,
"reasoning": "<2-3 sentences>",
"key_factors": ["factor1", "factor2"]
}Custom variable